Using Neural Networks for Candidate Selection and Well Performance Prediction in Water-Shutoff Treatments Using Polymer Gels - A Field-Case Study
- Alireza Saeedi (Chevron Corp.) | Kyle V. Camarda (The University of Kansas) | Jenn-Tai Liang (U. of Kansas)
- Document ID
- Society of Petroleum Engineers
- SPE Production & Operations
- Publication Date
- November 2007
- Document Type
- Journal Paper
- 417 - 424
- 2007. Society of Petroleum Engineers
- 5.1 Reservoir Characterisation, 5.1.5 Geologic Modeling, 1.6 Drilling Operations, 5.5 Reservoir Simulation, 7.6.6 Artificial Intelligence, 4.6 Natural Gas, 5.6.1 Open hole/cased hole log analysis, 1.10.1 Drill string components and drilling tools (tubulars, jars, subs, stabilisers, reamers, etc), 4.3 Flow Assurance, 4.1.5 Processing Equipment, 6.1.5 Human Resources, Competence and Training, 3 Production and Well Operations, 2.2.2 Perforating, 4.1.2 Separation and Treating, 3.2.3 Hydraulic Fracturing Design, Implementation and Optimisation
- 3 in the last 30 days
- 793 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 12.00|
|SPE Non-Member Price:||USD 35.00|
Using actual field cases, a neural network model was developed to identify candidate wells and predict well performance for water shutoff treatments using polymer gels. A feed forward back propagation algorithm was used to develop the neural networks. The before and after treatment data for 22 wells treated with polymer gels in the Arbuckle formation in central Kansas were used to train and verify the neural networks.
Polymers and gels have been used extensively in field applications to suppress excess water production and improve oil productivity. Field experience has demonstrated that candidate-well selection is critical to the success of gel-polymer treatments. To date, most candidate-well selections are on the basis of anecdotal screening guidelines, which often results in inconsistent treatment outcomes. With only pretreatment well data as input parameters, the neural networks developed in this work can accurately predict the post-treatment cumulative oil production of the well one month after treatment with an average error of 16%, and the post-treatment cumulative oil production three months after treatment with an average error of 10%. This is a dramatic improvement over the current method of using anecdotal screening guidelines for candidate-well selections.
This method represents a major breakthrough where the candidate selection can now be on the basis of the accurate predictions of treatment outcomes without having to use complicated reservoir models to simulate the well performance after treatment.
Excess water production is a major issue in oil field operations worldwide, currently averaging three barrels of water for each barrel of oil produced (Bailey et al. 2000). The situation is even worse in the US where more than seven barrels of water are produced for each barrel of oil (EPA 1999). The annual cost of treating and disposal of this water is estimated to be USD 40 billion (Bailey et al. 2000). Water shutoff and conformance control, therefore, represents a significant financial and environmental challenge/incentive for the petroleum industry. Polymers and gels have been used extensively in field applications to suppress excess water production and improve oil productivity (Seright et al. 2003). Field experience has demonstrated that candidate-well selection is critical to the success of gel-polymer treatments (Seright et al. 2003). To date, most candidate-well selections are on the basis of anecdotal screening guidelines, which often results in inconsistent treatment outcomes (Seright et al. 2003).
Reservoir simulation can potentially be used as a screening tool to predict the post-treatment performance of a candidate well using the pre-treatment historical data (Barati et al. 2006). However, this method is usually expensive and also requires extensive knowledge of the target reservoir (including the rock and fluid properties) the historical production data, and the geological reservoir model. Unfortunately, they are not always available for older reservoirs where the well records are often incomplete or lost (Barati et al. 2006).
Another method that has been investigated is to correlate the historical pre- and post-treatment performance data of the wells treated with polymer gels in the target reservoir. In this method, multivariate analysis is used to correlate the post-treatment performance of the treated wells with the pre-treatment data such as the geographical location of the wells, the depth of the wells, and the production history of the wells, and so on. The correlation could then be used as a predictive tool for candidate selection in the target reservoir. The problem with this method is that the physical processes involved in gel polymer treatment downhole are too complex to be accurately represented by correlations generated between pre- and post-treatment data using multivariate analysis (Alhajeri et al. 2006).
Prediction of the performance of a well after treatment, using the pre-treatment data, is a pattern recognition problem. Neural networks have shown great capabilities in solving pattern recognition problems (Ali 1994; Mohaghegh 1995; Ahmed et al. 1997). The objective of this study is to develop a methodology using neural networks to identify candidate wells on the basis of the predicted outcomes for gel-polymer treatments. The before and after treatment data for 22 wells treated with polymer gels in the Arbuckle formation in central Kansas were used to develop the neural networks (Saeedi 2005).
The Arbuckle formation is the main oil producer in Kansas, responsible for approximately 36% (~2.2 billion barrels) of the total produced oil in Kansas (Franseen et al. 1999) (see Fig. 1). Arbuckle reservoirs are fracture-controlled karstic reservoirs with porosity and permeability influenced by basement structural patterns and subaerial exposures. The subaerial exposure has resulted in weathering and secondary dissolution of the upper beds of the Arbuckle. It is believed that these processes have significantly increased porosity and permeability and created petroleum reservoirs in these strata. (Franseen et al. 1999). Shallow-shelf dolomites predominantly constitute the Arbuckle formation. Porosity of the Arbuckle reservoirs is enhanced by the dolomitization process (Franseen et al. 1999). Most of the Arbuckle's oil and gas zones are perforated in the top 25 ft of the Arbuckle, while some are perforated at a depth of 25 to 50 ft within the formation (Franseen et al. 1999). High initial oil productivity, a rapid decline in oil production rate, and the production of large amounts of water at high water to oil ratios (WOR) are characteristics of Arbuckle wells (Willhite and Pancake 2004). On the basis of these characteristics, Arbuckle reservoirs have been visualized as a column of oil on top of a strong aquifer. To prevent water coning, most of the wells in the Arbuckle were drilled relatively shallow into the formation(less than 10 ft) and completed open hole (Franseen et al. 1999). Because of the absence of field cores and the lack of well log data for the full productive intervals, the reservoir characteristics of the Arbuckle formation are not well understood.
|File Size||1 MB||Number of Pages||8|
Al-Fattah, S.M., and Startzman, R.A. 2001. Predicting Natural Gas ProductionUsing Artificial Neural Network. Paper SPE 68593 presented at the 2001 SPEHydrocarbon Economics and Evaluation Symposium, Dallas, 2-3 April. DOI:10.2118/68593-MS.
Ahmed, T., Link, C.A., Porter, K.W., et al. 1997. Application of Neural NetworkParameter Prediction in Reservoir Characterization and Simulation—A CaseHistory: The Rabbit Hills Field. Paper SPE 38985 presented at the SPE LatinAmerican and Caribbean Petroleum Engineering Conference and Exhibition, Rio deJaneiro, Brazil, 30 August-3 September. DOI: 10.2118/38985-MS.
Alhajeri, M.M., Green, D.W., Liang, J., and Pancake, R.E. 2006. Gel-PolymerExtends Arbuckle High-Water-Cut Well Life. Oil & Gas J. 104(2): 39-43.
Ali, J.K. 1994. NeuralNetworks: A New Tool for the Petroleum Industry? Paper SPE 27561 presentedat the SPE European Petroleum Computer Conference, Aberdeen, 15-17 March. DOI:10.2118/27561-MS.
Artificial Intelligence Softwares for Science and Business Ward SystemGroup, Inc., http://www.wardsystems.com. Downloaded10 October 2007.
Bailey, B., Crabtree, M., and Tyrie, J. 2000. Water Control. OilfieldReview 12 (1): 30-51.
Barati, R., Green, D.W., and Liang, J.T. 2006. Simulation of Gelled PolymerTreatments in the Arbuckle Formation, Kansas. Paper SPE 100067 presented atthe SPE/DOE Symposium on Improved Oil Recovery, Tulsa, 22-26 April. DOI:10.2118/100067-MS.
Brierley, P.D. 1998. Some Practical Applications of Neural Networks in theElectricity Industry. Doctor of Engineering thesis, Cranfield University,UK.
Centilmen, A., Ertekin, T., and Grader, A.S. 1999. Application of Neural Networks inMultiwell Field Development. Paper SPE 56433 presented at the SPE AnnualTechnical Conference and Exhibition, Houston, 3-6 October. DOI:10.2118/56433-MS.
EPA/310-R-99-006, Profile of the Oil and Gas Extraction Industry.1999. EPA.
Franseen, E.K., Byrnes, A.P., Cansler, J.R., Steinhauff, D.M., Carr, T.R.,and Dubois, M.K. 1999. Geologic Controls On Variable Character Of ArbuckleReservoirs In Kansas: An Emerging Picture. Kansas Geological Survey Open-fileReport 2003-59, University of Kansas, Lawrence, KS.
Keltch, B., 2003. Neuro3 software, developed by TRW: http://www.keltch.com/neuro3.html.Downloaded 10 October 2007.
Mohaghegh, S. 1995. NeuralNetwork: What It Can Do for Petroleum Engineers. JPT 47 (1):42. SPE-29219-PA. DOI: 10.2118/29219-PA.
Mohaghegh, S., Reeves, S., and Hill, D. 2000. Development of an Intelligent SystemsApproach for Restimulation Candidate Selection. Paper SPE 59767 presentedat the SPE/CERI Technology Symposium, Calgary, 3-5 April. DOI:10.2118/59767-MS.
Pham, T.D. and Liu, X. 1995. Neural Networks for Identification,Prediction and Control. London:Springler-Verlag.
Picton, P. 2000. Neural Networks. PALGRAVE, New York City (2000).
Portwood, J.T. 2005. The KansasArbuckle Formation: Performance Evaluation and Lessons Learned From More Than200 Polymer-Gel Water-Shutoff Treatments. Paper SPE 94096 presented at theSPE Production and Operations Symposium, Oklahoma City, Oklahoma, 16-19 April.DOI: 10.2118/94096-MS.
Saeedi, A. 2005. Candidate Selection and Well Performance Prediction forGel-Polymer Treatments Using Neural Networks. 2005. M.S. Thesis, University ofKansas, Lawrence, Kansas.
McVey, D.S., and Mohaghegh, S. 1994. Identification of ParametersInfluencing the Response of Gas Storage Wells to Hydraulic Fracturing With theAid of a Neural Network. SPE Computer Applications12 (4): 54-57. SPE-29159-PA. DOI: 10.2118/29159-PA.
Mohaghegh, S., Mohamad, K., Popa, A., Ameri, S., and Wood, D. 1999. Performance Drivers in Restimulationof Gas-Storage Wells. Paper SPE 57453 presented at the 1999 SPE EasternRegional Meeting, Charleston, West Virginia, 21-22 October. DOI:10.2118/57453-MS.
Oberwinkler, C. and Economides, M.J. 2003. The Definitive Identification ofCandidate Wells for Refracturing. Paper SPE 84211 presented at the 2003 SPEAnnual Technical Conference and Exhibition, Denver, 5-8 October.DOI:10.2118/84211-MS.
Seright, R.S., Lane, R.H., and Sydansk, R.D. 2003. A Strategy for Attacking Excess WaterProduction. SPEPF (18) 3: 158-169. SPE-84966-PA. DOI:10.2118/84966-PA.
Shelley, R.F. 1999. ArtificialNeural Networks Identify Restimulation Candidates in the Red Oak Field.Paper SPE 52190 presented at the 1999 SPE Mid-Continent Operations Symposium,Oklahoma City, Oklahoma, 28-31 March. DOI: 10.2118/52190-MS.
Swingler, K 1996. Applying Neural Networks, Practical Guide. SanFrancisco: Academic Press.
Willhite, G.P., and Pancake, R.E. 2004. Controlling Water Production UsingGelled Polymer Systems. Paper SPE 89464 presented at the SPE/DOE Symposiumon Improved Oil Recovery, Tulsa, 17-21 April. DOI: 10.2118/89464-MS.